Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Introduction to Learning01:18

Introduction to Learning

598
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
598
Associative Learning01:27

Associative Learning

659
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
659
Observational Learning01:12

Observational Learning

374
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
374
Distributed Loads: Problem Solving01:21

Distributed Loads: Problem Solving

814
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
814
Cognitive Learning01:21

Cognitive Learning

696
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
696
Distribution Reliability and Automation01:25

Distribution Reliability and Automation

174
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
174

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Novel strategy in giant cutaneous squamous cell carcinoma treatment: The case experience with a combination of photodynamic therapy and surgery.

Photodiagnosis and photodynamic therapy·2017
Same author

A Rice NAC Transcription Factor Promotes Leaf Senescence via ABA Biosynthesis.

Plant physiology·2017
Same author

Surface-rough Fe-N/C composite wrapped on carbon nanotubes as efficient electrocatalyst for oxygen reduction reaction.

Nanotechnology·2017
Same author

lncRNA HOXD-AS1 Regulates Proliferation and Chemo-Resistance of Castration-Resistant Prostate Cancer via Recruiting WDR5.

Molecular therapy : the journal of the American Society of Gene Therapy·2017
Same author

Transformation of Nitrogen and Evolution of N-Containing Species during Algae Pyrolysis.

Environmental science & technology·2017
Same author

Adult Attachment Styles Associated with Brain Activity in Response to Infant Faces in Nulliparous Women: An Event-Related Potentials Study.

Frontiers in psychology·2017

Related Experiment Videos

A Unified Framework for Automatic Distributed Active Learning.

Xu Chen, Brett Wujek

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |November 23, 2021
    PubMed
    Summary

    We introduce Automated Distributed Active Learning (AutoDAL), a unified framework for efficient machine learning with limited or imbalanced data. AutoDAL enhances scalability and performance on big data challenges.

    Area of Science:

    • Machine Learning
    • Data Science
    • Artificial Intelligence

    Background:

    • Active learning (AL) faces challenges with limited labeled data, imbalanced datasets, and scalability.
    • Automated hyperparameter selection is crucial for optimizing AL performance.
    • Existing methods struggle with big data and diverse dataset characteristics.

    Purpose of the Study:

    • To propose a novel unified framework for Automated Distributed Active Learning (AutoDAL).
    • To address key challenges in active learning including data limitations, imbalance, and scalability.
    • To enable automatic hyperparameter selection and efficient optimization for diverse datasets.

    Main Methods:

    • Automated graph-based semi-supervised learning with joint hyperparameter optimization.

    Related Experiment Videos

  • Clustering-based uncertainty sampling with maximum entropy (CME) loss for dense data.
  • Shrinkage optimized KL-divergence regularization and local selection based active learning (SOAR) loss for sparse/imbalanced data.
  • Optimization via iterative genetic algorithm (GA) with local generating set search (GSS) and integer linear programming (ILP).
  • Development of an efficient, scalable distributed active learning algorithm.

    • Main Results:

    • AutoDAL demonstrates superior performance on benchmark and real-world datasets (ECG, credit fraud).
    • The framework effectively handles limited labeled data and imbalanced datasets.
    • Significant performance improvements are observed compared to state-of-the-art AutoML and active learning algorithms.
    • The proposed distributed approach ensures scalability for big data applications.

    Conclusions:

    • AutoDAL provides a robust and scalable solution for automated distributed active learning.
    • The framework successfully integrates various techniques to address diverse data challenges.
    • AutoDAL offers significant advantages over existing methods in terms of performance and efficiency.